Abstract: Described embodiments relate to a method operable in a biometric authentication system. The method comprises initiating generation of an acoustic stimulus for application to a user's ear; and determining a quality measure of a response signal to the acoustic stimulus. Responsive to determining that the quality measure is inadequate for performing a biometric process, the method comprises one or more of: (i) modifying one or more properties of the acoustic stimulus to improve a signal to noise ratio, SNR, of the response signal and (ii) cancelling the effect of noise from outside the ear on the response signal of the user's ear to the acoustic stimulus to improve the SNR of the response signal.

Abstract: A method for adjusting playing sound in a sound playing system is disclosed. The sound playing system includes a camera module, a facial analysis module, a sound inputting module, a sound adjustment module, and a speaker. The method includes: obtaining an image of a face of each one of a plurality of people through the camera module; analyzing the image to estimate the age of each one of the plurality of people through the facial analysis module, and obtaining a target age according to the age of each person; obtaining a playing sound through the sound inputting module; adjusting the playing sound according to the target age through the sound adjustment module to obtain an output sound; and playing the output sound through the speaker.

Abstract: An electrical current generating device having a sound wave force magnifying structure in the form of a force transmission pin which is longitudinally slidable within a body bore and having a proximal end of a large area for receiving sound wave forces, and having a greatly reduced area distal end which bears on a piezoelectric element.

Abstract: Methods, systems, and computer program products for detecting anomalous behavior include reconstructing a waveform of a target device from an input waveform using a target autoencoder. A waveform of unrelated sound events is reconstructed from the input waveform using an environmental autoencoder. The input waveform is classified to determine that the input waveform is produced by anomalous behavior of the target device using a classifier, based on the reconstructed waveform of the target device and the reconstructed waveform of the unrelated sound events. An automatic response to the anomalous behavior is generated.

Abstract: A power amplifying device according to an embodiment includes three or more BTL amplifiers and a closed loop section. The three or more BTL amplifiers include bridge-connected first and second output amplifiers and output a first output signal obtained by amplifying a first input signal. Switch circuits respectively corresponding to the three or more BTL amplifiers are connected in series in the closed loop section. The closed loop section is capable of forming a closed loop. An output terminal of the second output amplifier is connected to one end of the switch circuit corresponding to the second output amplifier. The switch circuit is turned on to establish connection between an output terminal of the first output amplifier and the output terminal of the second output amplifier and is turned off to break the connection between the output terminals.

Abstract: A guitar amplifier and a control method of a guitar amplifier in which a setting of a performance mode can be easily changed without an interruption to a sound is provided. The guitar amplifier, which performs musical sound processing on an input musical sound and outputs it, includes a storage device which stores a plurality of information sets including a set value for each of one or two or more types of musical sound processing used in a performance mode, and a control device which changes the setting of the one or two or more types of musical sound processing to a setting according to a set value of a selected information set when information indicating ON of the performance mode, to which the selected information set from the plurality of information sets has been applied, is input.

Abstract: An original noisy signal of each of at least two microphones is acquired by acquiring, using the at least two microphones, an audio signal emitted by each sound source. For each frame in time domain, an estimated frequency-domain signal of each sound source is acquired according to the original noisy signal of each of the at least two microphones. A frequency collection containing a plurality of predetermined static frequencies and dynamic frequencies is determined in a predetermined frequency band range. A weighting coefficient of each frequency contained in the frequency collection is determined according to the estimated frequency-domain signal of the each frequency in the frequency collection. A separation matrix of the each frequency is determined according to the weighting coefficient. The audio signal emitted by each of the at least two sound sources is acquired based on the separation matrix and the original noisy signal.

Abstract: At least one embodiment is directed to a method for automatically activating ambient sound pass-through in an earphone in response to a detected keyword in the ambient sound field of the earphone user, the steps of the method comprising at least receiving at least one ambient sound microphone (ASM) signal; receiving at least one audio content (AC) signal; and comparing the ASM signal to a keyword and if the ASM signal matches a keyword then an AC gain is created.

Abstract: A headphones system includes reference headphones having native audio performance characteristics, and a personal communication device that generates a user interface presenting visual representations of other headphones. In response to user selection of a visual representation of particular headphones, the personal communication device identifies a corresponding current sound profile establishing a mapping between audio performance characteristics of the particular user selected headphones and the native audio performance characteristics, and communicates the current sound profile to the reference headphones.

Abstract: Systems and methods for sound source detection and localization utilizing an autonomous driving vehicle (ADV) are disclosed. The method includes receiving audio data from a number of audio sensors mounted on the ADV. The audio data comprises sounds captured by the audio sensors and emitted by one or more sound sources. Based on the received audio data, the method further includes determining a number of sound source information. Each sound source information comprises a confidence score associated with an existence of a specific sound. The method further includes generating a data representation to report whether there exists the specific sound within the driving environment of the ADV. The data representation comprises the determined sound source information. The received audio data and the generated data representation are utilized to subsequently train a machine learning algorithm to recognize the specific sound source during autonomous driving of the ADV in real-time.

Abstract: The present disclosure relates to a display apparatus, and more particularly, to a display apparatus having a display panel capable of generating sound. A display apparatus according to the present disclosure includes: a display module; a guide panel disposed at circumferences of a rear surface of the display module; a back cover attached to the guide panel; a sound generating unit disposed between the display module and the back cover; and an adhesive fixing element and a vibration absorber disposed between the guide panel and the rear surface of the display module, wherein the adhesive fixing element fasten the guide panel to the rear surface of the display module, and wherein the vibration absorber is disposed at the guide panel as facing to inner portions of the display module.

Abstract: A method, apparatus and computer program product are provided to identify the class of vehicle driving over a road surface based upon audio data collected as the vehicle drives thereover. With respect to predicting a class of a vehicle, audio data is obtained that is created by the vehicle while driving over the road surface. The audio data includes one or more audio frequency features and/or one or more audio amplitude features. The audio data including the one or more audio frequency features and/or the one or more audio amplitude features is provided to a machine learning model and the class of the vehicle that created the audio data is predicted utilizing the machine learning model. A method, apparatus and computer program product are also provided for training the machine learning model to predict the class of the vehicle driving over the road surface.

Abstract: Methods and systems for localizing a sound source include determining a spatial transformation between a position of a reference microphone array and a position of a displaced microphone array. A sound is measured at the reference microphone array and at the displaced microphone array. A source of the sound is localized using a neural network that includes respective paths for the reference microphone array and the displaced microphone array. The neural network further includes a transformation layer that represents the spatial transformation.

Abstract: Methods and a system that automatically determines the spatial relationship of microphone assemblies with respect to a camera of a video conference endpoint through audio signal processing. The video conference endpoint may include at least a microphone assembly and a loudspeaker. The microphone assembly may include a plurality of co-located directional microphones. The video conference endpoint may detect, by the plurality of co-located directional microphones of the microphone assembly, audio emitted from the loudspeaker of the video conference endpoint. The video conference endpoint may then generate data representing a spatial relationship of the microphone assembly with respect to the loudspeaker based on a compilation of the audio detected by the co-located directional microphones of the microphone assembly.

Abstract: In various embodiments, a group photograph system coordinates and creates a group photograph of participants of a video conferencing session. Using inputs from the participants, the group photograph system captures images of individual participants and selectively assembles a group photograph based on the rating of each individual participant. In one embodiment, the group photograph system sends a countdown signal to a first participant and a second participant wherein the first participant and the second participant are part of a group photograph within a video conferencing session wherein the countdown signal represents an amount of time before a first participant image is captured of the first participant. In another embodiment, the group photography system captures the first participant image and a second participant image of the first participant and the second participant, respectively and creates a first group photograph which includes the first participant image and the second participant image.

Abstract: Provided is a training method of a neural network that is applied to an audio signal encoding method using an audio signal encoding apparatus, the training method including generating a masking threshold of a first audio signal before training is performed, calculating a weight matrix to be applied to a frequency component of the first audio signal based on the masking threshold, generating a weighted error function obtained by correcting a preset error function using the weight matrix, and generating a second audio signal by applying a parameter learned using the weighted error function to the first audio signal.

Abstract: A vehicle that efficiently prevents a driver from eavesdropping a voice of a passenger may include: a driver's seat having a headrest speaker in a headrest thereof; the headrest speaker configured to output a sound, a front passenger seat, at least one rear passenger seat; a microphone configured to detect a voice of the passenger seated on the at least one rear passenger seat; and a controller configured to generate a masking curve based on the voice of the passenger and output a masking sound corresponding to the masking curve by controlling the headrest speaker.

Abstract: A method of discouraging theft of a set of headphones from a rightful user includes, when first connecting the headphones to a first cell phone, requesting transmission of an ID number for the first cell phone from the first cell phone to the headphones, requesting the rightful user to provide a personal identification number (PIN) for the headphones; and storing the ID number and PIN in the headphones. At any subsequent attempt by a user to connect the headphones to a second cell phone, the second cell phone's ID number is requested and compared with the stored ID number for the first cell phone. If the ID numbers match, full functional connection between the headphones and the second cell phone is allowed, but if they do not, full functional connection is blocked until the user provides the PIN for the set of headphones.

Abstract: Systems and methods are provided for circuit configurations that maintain audio playback performance while reducing power consumption. In particular, a gain for a current analog-to-digital converter in an audio playback path is adjusted based on an amplitude of the input signal. Additionally, systems and methods are provided for transitioning between a modes of operation for large signals and mode of operation for small signals.

Abstract: A device includes one or more processors configured to provide audio data samples to a sound event classification model. The one or more processors are also configured to determine, based on an output of the sound event classification model responsive to the audio data samples, whether a sound class of with the audio data samples was recognized by the sound event classification model. The one or more processors are further configured to, based on a determination that the sound class was not recognized, determine whether the sound event classification model corresponds to an audio scene associated with the audio data samples. The one or more processors are also configured to, based on a determination that the sound event classification model corresponds to the audio scene associated with the audio data samples, store model update data based on the audio data samples.